Introduce LZ4 compression backend and make it available for selection.
LZ4 support is optional and requires user to set ZRAM_LZ4_COMPRESS config
option. The default compression backend is LZO.
TEST
(x86_64, core i5, 2 cores + 2 hyperthreading, zram disk size 1G,
ext4 file system, 3 compression streams)
iozone -t 3 -R -r 16K -s 60M -I +Z
Test LZO LZ4
----------------------------------------------
Initial write 1642744.62 1317005.09
Rewrite 2498980.88 1800645.16
Read 3957026.38 5877043.75
Re-read 3950997.38 5861847.00
Reverse Read 2937114.56 5047384.00
Stride read 2948163.19 4929587.38
Random read 3292692.69 4880793.62
Mixed workload 1545602.62 3502940.38
Random write 2448039.75 1758786.25
Pwrite 1670051.03 1338329.69
Pread 2530682.00 5097177.62
Fwrite 3232085.62 3275942.56
Fread 6306880.25 6645271.12
So on my system LZ4 is slower in write-only tests, while it performs
better in read-only and mixed (reads + writes) tests.
Official LZ4 benchmarks available here http://code.google.com/p/lz4/
(linux kernel uses revision r90).
Signed-off-by: Sergey Senozhatsky <sergey.senozhatsky@gmail.com>
Acked-by: Minchan Kim <minchan@kernel.org>
Cc: Jerome Marchand <jmarchan@redhat.com>
Cc: Nitin Gupta <ngupta@vflare.org>
Signed-off-by: Andrew Morton <akpm@linux-foundation.org>
Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
This patch allows to change max_comp_streams on initialised zcomp.
Introduce zcomp set_max_streams() knob, zcomp_strm_multi_set_max_streams()
and zcomp_strm_single_set_max_streams() callbacks to change streams limit
for zcomp_strm_multi and zcomp_strm_single, accordingly. set_max_streams
for single steam zcomp does nothing.
If user has lowered the limit, then zcomp_strm_multi_set_max_streams()
attempts to immediately free extra streams (as much as it can, depending
on idle streams availability).
Note, this patch does not allow to change stream 'policy' from single to
multi stream (or vice versa) on already initialised compression backend.
Signed-off-by: Sergey Senozhatsky <sergey.senozhatsky@gmail.com>
Acked-by: Minchan Kim <minchan@kernel.org>
Cc: Jerome Marchand <jmarchan@redhat.com>
Cc: Nitin Gupta <ngupta@vflare.org>
Signed-off-by: Andrew Morton <akpm@linux-foundation.org>
Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
Existing zram (zcomp) implementation has only one compression stream
(buffer and algorithm private part), so in order to prevent data
corruption only one write (compress operation) can use this compression
stream, forcing all concurrent write operations to wait for stream lock
to be released. This patch changes zcomp to keep a compression streams
list of user-defined size (via sysfs device attr). Each write operation
still exclusively holds compression stream, the difference is that we
can have N write operations (depending on size of streams list)
executing in parallel. See TEST section later in commit message for
performance data.
Introduce struct zcomp_strm_multi and a set of functions to manage
zcomp_strm stream access. zcomp_strm_multi has a list of idle
zcomp_strm structs, spinlock to protect idle list and wait queue, making
it possible to perform parallel compressions.
The following set of functions added:
- zcomp_strm_multi_find()/zcomp_strm_multi_release()
find and release a compression stream, implement required locking
- zcomp_strm_multi_create()/zcomp_strm_multi_destroy()
create and destroy zcomp_strm_multi
zcomp ->strm_find() and ->strm_release() callbacks are set during
initialisation to zcomp_strm_multi_find()/zcomp_strm_multi_release()
correspondingly.
Each time zcomp issues a zcomp_strm_multi_find() call, the following set
of operations performed:
- spin lock strm_lock
- if idle list is not empty, remove zcomp_strm from idle list, spin
unlock and return zcomp stream pointer to caller
- if idle list is empty, current adds itself to wait queue. it will be
awaken by zcomp_strm_multi_release() caller.
zcomp_strm_multi_release():
- spin lock strm_lock
- add zcomp stream to idle list
- spin unlock, wake up sleeper
Minchan Kim reported that spinlock-based locking scheme has demonstrated
a severe perfomance regression for single compression stream case,
comparing to mutex-based (see https://lkml.org/lkml/2014/2/18/16)
base spinlock mutex
==Initial write ==Initial write ==Initial write
records: 5 records: 5 records: 5
avg: 1642424.35 avg: 699610.40 avg: 1655583.71
std: 39890.95(2.43%) std: 232014.19(33.16%) std: 52293.96
max: 1690170.94 max: 1163473.45 max: 1697164.75
min: 1568669.52 min: 573429.88 min: 1553410.23
==Rewrite ==Rewrite ==Rewrite
records: 5 records: 5 records: 5
avg: 1611775.39 avg: 501406.64 avg: 1684419.11
std: 17144.58(1.06%) std: 15354.41(3.06%) std: 18367.42
max: 1641800.95 max: 531356.78 max: 1706445.84
min: 1593515.27 min: 488817.78 min: 1655335.73
When only one compression stream available, mutex with spin on owner
tends to perform much better than frequent wait_event()/wake_up(). This
is why single stream implemented as a special case with mutex locking.
Introduce and document zram device attribute max_comp_streams. This
attr shows and stores current zcomp's max number of zcomp streams
(max_strm). Extend zcomp's zcomp_create() with `max_strm' parameter.
`max_strm' limits the number of zcomp_strm structs in compression
backend's idle list (max_comp_streams).
max_comp_streams used during initialisation as follows:
-- passing to zcomp_create() max_strm equals to 1 will initialise zcomp
using single compression stream zcomp_strm_single (mutex-based locking).
-- passing to zcomp_create() max_strm greater than 1 will initialise zcomp
using multi compression stream zcomp_strm_multi (spinlock-based locking).
default max_comp_streams value is 1, meaning that zram with single stream
will be initialised.
Later patch will introduce configuration knob to change max_comp_streams
on already initialised and used zcomp.
TEST
iozone -t 3 -R -r 16K -s 60M -I +Z
test base 1 strm (mutex) 3 strm (spinlock)
-----------------------------------------------------------------------
Initial write 589286.78 583518.39 718011.05
Rewrite 604837.97 596776.38 1515125.72
Random write 584120.11 595714.58 1388850.25
Pwrite 535731.17 541117.38 739295.27
Fwrite 1418083.88 1478612.72 1484927.06
Usage example:
set max_comp_streams to 4
echo 4 > /sys/block/zram0/max_comp_streams
show current max_comp_streams (default value is 1).
cat /sys/block/zram0/max_comp_streams
Signed-off-by: Sergey Senozhatsky <sergey.senozhatsky@gmail.com>
Acked-by: Minchan Kim <minchan@kernel.org>
Cc: Jerome Marchand <jmarchan@redhat.com>
Cc: Nitin Gupta <ngupta@vflare.org>
Signed-off-by: Andrew Morton <akpm@linux-foundation.org>
Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
This is preparation patch to add multi stream support to zcomp.
Introduce struct zcomp_strm_single and a set of functions to manage
zcomp_strm stream access. zcomp_strm_single implements single compession
stream, same way as current zcomp implementation. This moves zcomp_strm
stream control and locking from zcomp, so compressing backend zcomp is not
aware of required locking.
Single and multi streams require different locking schemes. Minchan Kim
reported that spinlock-based locking scheme (which is used in multi stream
implementation) has demonstrated a severe perfomance regression for single
compression stream case, comparing to mutex-based. see
https://lkml.org/lkml/2014/2/18/16
The following set of functions added:
- zcomp_strm_single_find()/zcomp_strm_single_release()
find and release a compression stream, implement required locking
- zcomp_strm_single_create()/zcomp_strm_single_destroy()
create and destroy zcomp_strm_single
New ->strm_find() and ->strm_release() callbacks added to zcomp, which are
set to zcomp_strm_single_find() and zcomp_strm_single_release() during
initialisation. Instead of direct locking and zcomp_strm access from
zcomp_strm_find() and zcomp_strm_release(), zcomp now calls ->strm_find()
and ->strm_release() correspondingly.
Signed-off-by: Sergey Senozhatsky <sergey.senozhatsky@gmail.com>
Acked-by: Minchan Kim <minchan@kernel.org>
Cc: Jerome Marchand <jmarchan@redhat.com>
Cc: Nitin Gupta <ngupta@vflare.org>
Signed-off-by: Andrew Morton <akpm@linux-foundation.org>
Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
ZRAM performs direct LZO compression algorithm calls, making it the one
and only option. While LZO is generally performs well, LZ4 algorithm
tends to have a faster decompression (see http://code.google.com/p/lz4/
for full report)
Name Ratio C.speed D.speed
MB/s MB/s
LZ4 (r101) 2.084 422 1820
LZO 2.06 2.106 414 600
Thus, users who have mostly read (decompress) usage scenarious or mixed
workflow (writes with relatively high read ops number) will benefit from
using LZ4 compression backend.
Introduce compressing backend abstraction zcomp in order to support
multiple compression algorithms with the following set of operations:
.create
.destroy
.compress
.decompress
Schematically zram write() usually contains the following steps:
0) preparation (decompression of partioal IO, etc.)
1) lock buffer_lock mutex (protects meta compress buffers)
2) compress (using meta compress buffers)
3) alloc and map zs_pool object
4) copy compressed data (from meta compress buffers) to object allocated by 3)
5) free previous pool page, assign a new one
6) unlock buffer_lock mutex
As we can see, compressing buffers must remain untouched from 1) to 4),
because, otherwise, concurrent write() can overwrite data. At the same
time, zram_meta must be aware of a) specific compression algorithm memory
requirements and b) necessary locking to protect compression buffers. To
remove requirement a) new struct zcomp_strm introduced, which contains a
compress/decompress `buffer' and compression algorithm `private' part.
While struct zcomp implements zcomp_strm stream handling and locking and
removes requirement b) from zram meta. zcomp ->create() and ->destroy(),
respectively, allocate and deallocate algorithm specific zcomp_strm
`private' part.
Every zcomp has zcomp stream and mutex to protect its compression stream.
Stream usage semantics remains the same -- only one write can hold stream
lock and use its buffers. zcomp_strm_find() turns caller into exclusive
user of a stream (holding stream mutex until zram release stream), and
zcomp_strm_release() makes zcomp stream available (unlock the stream
mutex). Hence no concurrent write (compression) operations possible at
the moment.
iozone -t 3 -R -r 16K -s 60M -I +Z
test base patched
--------------------------------------------------
Initial write 597992.91 591660.58
Rewrite 609674.34 616054.97
Read 2404771.75 2452909.12
Re-read 2459216.81 2470074.44
Reverse Read 1652769.66 1589128.66
Stride read 2202441.81 2202173.31
Random read 2236311.47 2276565.31
Mixed workload 1423760.41 1709760.06
Random write 579584.08 615933.86
Pwrite 597550.02 594933.70
Pread 1703672.53 1718126.72
Fwrite 1330497.06 1461054.00
Fread 3922851.00 3957242.62
Usage examples:
comp = zcomp_create(NAME) /* NAME e.g. "lzo" */
which initialises compressing backend if requested algorithm is supported.
Compress:
zstrm = zcomp_strm_find(comp)
zcomp_compress(comp, zstrm, src, &dst_len)
[..] /* copy compressed data */
zcomp_strm_release(comp, zstrm)
Decompress:
zcomp_decompress(comp, src, src_len, dst);
Free compessing backend and its zcomp stream:
zcomp_destroy(comp)
Signed-off-by: Sergey Senozhatsky <sergey.senozhatsky@gmail.com>
Acked-by: Minchan Kim <minchan@kernel.org>
Cc: Jerome Marchand <jmarchan@redhat.com>
Cc: Nitin Gupta <ngupta@vflare.org>
Signed-off-by: Andrew Morton <akpm@linux-foundation.org>
Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
allocate new `zram_meta' in disksize_store() only for uninitialised zram
device, saving a number of allocations and deallocations in case if
disksize_store() was called on currently used device. at the same time
zram_meta stack variable is not necessary, because we can set ->meta
directly. there is also no need in setting QUEUE_FLAG_NONROT queue on
every disksize_store(), set it once during device creation.
[minchan@kernel.org: handle zram->meta alloc fail case]
[minchan@kernel.org: prevent lockdep spew of init_lock]
Signed-off-by: Sergey Senozhatsky <sergey.senozhatsky@gmail.com>
Signed-off-by: Minchan Kim <minchan@kernel.org>
Acked-by: Jerome Marchand <jmarchan@redhat.com>
Cc: Sasha Levin <sasha.levin@oracle.com>
Signed-off-by: Andrew Morton <akpm@linux-foundation.org>
Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
Document `failed_reads' and `failed_writes' device attributes.
Remove info about `discard' - there is no such zram attr.
Signed-off-by: Sergey Senozhatsky <sergey.senozhatsky@gmail.com>
Cc: Minchan Kim <minchan@kernel.org>
Cc: Jerome Marchand <jmarchan@redhat.com>
Cc: Nitin Gupta <ngupta@vflare.org>
Signed-off-by: Andrew Morton <akpm@linux-foundation.org>
Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
zram accounted but did not report numbers of failed read and write
queries. make these stats available as failed_reads and failed_writes
attrs.
Signed-off-by: Sergey Senozhatsky <sergey.senozhatsky@gmail.com>
Acked-by: Minchan Kim <minchan@kernel.org>
Acked-by: Jerome Marchand <jmarchan@redhat.com>
Cc: Nitin Gupta <ngupta@vflare.org>
Signed-off-by: Andrew Morton <akpm@linux-foundation.org>
Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
This is a preparation patch for stats code duplication removal.
1) use atomic64_t for `pages_zero' and `pages_stored' zram stats.
2) `compr_size' and `pages_zero' struct zram_stats members did not
follow the existing device attr naming scheme: zram_stats.ATTR has
ATTR_show() function. rename them:
-- compr_size -> compr_data_size
-- pages_zero -> zero_pages
Minchan Kim's note:
If we really have trouble with atomic stat operation, we could
change it with percpu_counter so that it could solve atomic overhead and
unnecessary memory space by introducing unsigned long instead of 64bit
atomic_t.
Signed-off-by: Sergey Senozhatsky <sergey.senozhatsky@gmail.com>
Acked-by: Minchan Kim <minchan@kernel.org>
Acked-by: Jerome Marchand <jmarchan@redhat.com>
Cc: Nitin Gupta <ngupta@vflare.org>
Signed-off-by: Andrew Morton <akpm@linux-foundation.org>
Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
Remove `good' and `bad' compressed sub-requests stats. RW request may
cause a number of RW sub-requests. zram used to account `good' compressed
sub-queries (with compressed size less than 50% of original size), `bad'
compressed sub-queries (with compressed size greater that 75% of original
size), leaving sub-requests with compression size between 50% and 75% of
original size not accounted and not reported. zram already accounts each
sub-request's compression size so we can calculate real device compression
ratio.
Signed-off-by: Sergey Senozhatsky <sergey.senozhatsky@gmail.com>
Acked-by: Minchan Kim <minchan@kernel.org>
Acked-by: Jerome Marchand <jmarchan@redhat.com>
Cc: Nitin Gupta <ngupta@vflare.org>
Signed-off-by: Andrew Morton <akpm@linux-foundation.org>
Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
Do not pass rw argument down the __zram_make_request() -> zram_bvec_rw()
chain, decode it in zram_bvec_rw() instead. Besides, this is the place
where we distinguish READ and WRITE bio data directions, so account zram
RW stats here, instead of __zram_make_request(). This also allows to
account a real number of zram READ/WRITE operations, not just requests
(single RW request may cause a number of zram RW ops with separate
locking, compression/decompression, etc).
Signed-off-by: Sergey Senozhatsky <sergey.senozhatsky@gmail.com>
Acked-by: Minchan Kim <minchan@kernel.org>
Acked-by: Jerome Marchand <jmarchan@redhat.com>
Cc: Nitin Gupta <ngupta@vflare.org>
Signed-off-by: Andrew Morton <akpm@linux-foundation.org>
Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
Introduce init_done() helper function which allows us to drop `init_done'
struct zram member. init_done() uses the fact that ->init_done == 1
equals to ->meta != NULL.
Signed-off-by: Sergey Senozhatsky <sergey.senozhatsky@gmail.com>
Acked-by: Minchan Kim <minchan@kernel.org>
Acked-by: Jerome Marchand <jmarchan@redhat.com>
Cc: Nitin Gupta <ngupta@vflare.org>
Signed-off-by: Andrew Morton <akpm@linux-foundation.org>
Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
A new dump_page() routine was recently added, and marked
EXPORT_SYMBOL_GPL. dump_page() was also added to the VM_BUG_ON_PAGE()
macro, and so the end result is that non-GPL code can no longer call
get_page() and a few other routines.
This only happens if the kernel was compiled with CONFIG_DEBUG_VM.
Change dump_page() to be EXPORT_SYMBOL.
Longer explanation:
Prior to commit 309381feae ("mm: dump page when hitting a VM_BUG_ON
using VM_BUG_ON_PAGE") , it was possible to build MIT-licensed (non-GPL)
drivers on Fedora. Fedora is semi-unique, in that it sets
CONFIG_VM_DEBUG.
Because Fedora sets CONFIG_VM_DEBUG, they end up pulling in dump_page(),
via VM_BUG_ON_PAGE, via get_page(). As one of the authors of NVIDIA's
new, open source, "UVM-Lite" kernel module, I originally choose to use
the kernel's get_page() routine from within nvidia_uvm_page_cache.c,
because get_page() has always seemed to be very clearly intended for use
by non-GPL, driver code.
So I'm hoping that making get_page() widely accessible again will not be
too controversial. We did check with Fedora first, and they responded
(https://bugzilla.redhat.com/show_bug.cgi?id=1074710#c3) that we should
try to get upstream changed, before asking Fedora to change. Their
reasoning seems beneficial to Linux: leaving CONFIG_DEBUG_VM set allows
Fedora to help catch mm bugs.
Signed-off-by: John Hubbard <jhubbard@nvidia.com>
Cc: Sasha Levin <sasha.levin@oracle.com>
Cc: Josh Boyer <jwboyer@redhat.com>
Signed-off-by: Andrew Morton <akpm@linux-foundation.org>
Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
LAST_CPUPID_MASK is calculated using LAST_CPUPID_WIDTH. However
LAST_CPUPID_WIDTH itself can be 0. (when LAST_CPUPID_NOT_IN_PAGE_FLAGS is
set). In such a case LAST_CPUPID_MASK turns out to be 0.
But with recent commit 1ae71d0319: (mm: numa: bugfix for
LAST_CPUPID_NOT_IN_PAGE_FLAGS) if LAST_CPUPID_MASK is 0,
page_cpupid_xchg_last() and page_cpupid_reset_last() causes
page->_last_cpupid to be set to 0.
This causes performance regression. Its almost as if numa_balancing is
off.
Fix LAST_CPUPID_MASK by using LAST_CPUPID_SHIFT instead of
LAST_CPUPID_WIDTH.
Some performance numbers and perf stats with and without the fix.
(3.14-rc6)
----------
numa01
Performance counter stats for '/usr/bin/time -f %e %S %U %c %w -o start_bench.out -a ./numa01':
12,27,462 cs [100.00%]
2,41,957 migrations [100.00%]
1,68,01,713 faults [100.00%]
7,99,35,29,041 cache-misses
98,808 migrate:mm_migrate_pages [100.00%]
1407.690148814 seconds time elapsed
numa02
Performance counter stats for '/usr/bin/time -f %e %S %U %c %w -o start_bench.out -a ./numa02':
63,065 cs [100.00%]
14,364 migrations [100.00%]
2,08,118 faults [100.00%]
25,32,59,404 cache-misses
12 migrate:mm_migrate_pages [100.00%]
63.840827219 seconds time elapsed
(3.14-rc6 with fix)
-------------------
numa01
Performance counter stats for '/usr/bin/time -f %e %S %U %c %w -o start_bench.out -a ./numa01':
9,68,911 cs [100.00%]
1,01,414 migrations [100.00%]
88,38,697 faults [100.00%]
4,42,92,51,042 cache-misses
4,25,060 migrate:mm_migrate_pages [100.00%]
685.965331189 seconds time elapsed
numa02
Performance counter stats for '/usr/bin/time -f %e %S %U %c %w -o start_bench.out -a ./numa02':
17,543 cs [100.00%]
2,962 migrations [100.00%]
1,17,843 faults [100.00%]
11,80,61,644 cache-misses
12,358 migrate:mm_migrate_pages [100.00%]
20.380132343 seconds time elapsed
Signed-off-by: Srikar Dronamraju <srikar@linux.vnet.ibm.com>
Cc: Liu Ping Fan <pingfank@linux.vnet.ibm.com>
Reviewed-by: Aneesh Kumar K.V <aneesh.kumar@linux.vnet.ibm.com>
Cc: Peter Zijlstra <peterz@infradead.org>
Cc: Benjamin Herrenschmidt <benh@kernel.crashing.org>
Cc: Paul Mackerras <paulus@samba.org>
Cc: Mel Gorman <mel@csn.ul.ie>
Signed-off-by: Andrew Morton <akpm@linux-foundation.org>
Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
Commit f9acc8c7b3 ("readahead: sanify file_ra_state names") left
ra_submit with a single function call.
Move ra_submit to internal.h and inline it to save some stack. Thanks
to Andrew Morton for commenting different versions.
Signed-off-by: Fabian Frederick <fabf@skynet.be>
Suggested-by: Andrew Morton <akpm@linux-foundation.org>
Signed-off-by: Andrew Morton <akpm@linux-foundation.org>
Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
When I decrease the value of nr_hugepage in procfs a lot, softlockup
happens. It is because there is no chance of context switch during this
process.
On the other hand, when I allocate a large number of hugepages, there is
some chance of context switch. Hence softlockup doesn't happen during
this process. So it's necessary to add the context switch in the
freeing process as same as allocating process to avoid softlockup.
When I freed 12 TB hugapages with kernel-2.6.32-358.el6, the freeing
process occupied a CPU over 150 seconds and following softlockup message
appeared twice or more.
$ echo 6000000 > /proc/sys/vm/nr_hugepages
$ cat /proc/sys/vm/nr_hugepages
6000000
$ grep ^Huge /proc/meminfo
HugePages_Total: 6000000
HugePages_Free: 6000000
HugePages_Rsvd: 0
HugePages_Surp: 0
Hugepagesize: 2048 kB
$ echo 0 > /proc/sys/vm/nr_hugepages
BUG: soft lockup - CPU#16 stuck for 67s! [sh:12883] ...
Pid: 12883, comm: sh Not tainted 2.6.32-358.el6.x86_64 #1
Call Trace:
free_pool_huge_page+0xb8/0xd0
set_max_huge_pages+0x128/0x190
hugetlb_sysctl_handler_common+0x113/0x140
hugetlb_sysctl_handler+0x1e/0x20
proc_sys_call_handler+0x97/0xd0
proc_sys_write+0x14/0x20
vfs_write+0xb8/0x1a0
sys_write+0x51/0x90
__audit_syscall_exit+0x265/0x290
system_call_fastpath+0x16/0x1b
I have not confirmed this problem with upstream kernels because I am not
able to prepare the machine equipped with 12TB memory now. However I
confirmed that the amount of decreasing hugepages was directly
proportional to the amount of required time.
I measured required times on a smaller machine. It showed 130-145
hugepages decreased in a millisecond.
Amount of decreasing Required time Decreasing rate
hugepages (msec) (pages/msec)
------------------------------------------------------------
10,000 pages == 20GB 70 - 74 135-142
30,000 pages == 60GB 208 - 229 131-144
It means decrement of 6TB hugepages will trigger softlockup with the
default threshold 20sec, in this decreasing rate.
Signed-off-by: Masayoshi Mizuma <m.mizuma@jp.fujitsu.com>
Cc: Joonsoo Kim <iamjoonsoo.kim@lge.com>
Cc: Michal Hocko <mhocko@suse.cz>
Cc: Wanpeng Li <liwanp@linux.vnet.ibm.com>
Cc: Aneesh Kumar <aneesh.kumar@linux.vnet.ibm.com>
Cc: KOSAKI Motohiro <kosaki.motohiro@jp.fujitsu.com>
Cc: Naoya Horiguchi <n-horiguchi@ah.jp.nec.com>
Cc: <stable@vger.kernel.org>
Signed-off-by: Andrew Morton <akpm@linux-foundation.org>
Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
This is a small cleanup.
Signed-off-by: Emil Medve <Emilian.Medve@Freescale.com>
Signed-off-by: Andrew Morton <akpm@linux-foundation.org>
Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
There's only one caller of set_page_dirty_balance() and that will call it
with page_mkwrite == 0.
The page_mkwrite argument was unused since commit b827e496c8 "mm: close
page_mkwrite races".
Signed-off-by: Miklos Szeredi <mszeredi@suse.cz>
Signed-off-by: Andrew Morton <akpm@linux-foundation.org>
Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
A BUG_ON(!PageLocked) was triggered in mlock_vma_page() by Sasha Levin
fuzzing with trinity. The call site try_to_unmap_cluster() does not lock
the pages other than its check_page parameter (which is already locked).
The BUG_ON in mlock_vma_page() is not documented and its purpose is
somewhat unclear, but apparently it serializes against page migration,
which could otherwise fail to transfer the PG_mlocked flag. This would
not be fatal, as the page would be eventually encountered again, but
NR_MLOCK accounting would become distorted nevertheless. This patch adds
a comment to the BUG_ON in mlock_vma_page() and munlock_vma_page() to that
effect.
The call site try_to_unmap_cluster() is fixed so that for page !=
check_page, trylock_page() is attempted (to avoid possible deadlocks as we
already have check_page locked) and mlock_vma_page() is performed only
upon success. If the page lock cannot be obtained, the page is left
without PG_mlocked, which is again not a problem in the whole unevictable
memory design.
Signed-off-by: Vlastimil Babka <vbabka@suse.cz>
Signed-off-by: Bob Liu <bob.liu@oracle.com>
Reported-by: Sasha Levin <sasha.levin@oracle.com>
Cc: Wanpeng Li <liwanp@linux.vnet.ibm.com>
Cc: Michel Lespinasse <walken@google.com>
Cc: KOSAKI Motohiro <kosaki.motohiro@jp.fujitsu.com>
Acked-by: Rik van Riel <riel@redhat.com>
Cc: David Rientjes <rientjes@google.com>
Cc: Mel Gorman <mgorman@suse.de>
Cc: Hugh Dickins <hughd@google.com>
Cc: Joonsoo Kim <iamjoonsoo.kim@lge.com>
Cc: <stable@vger.kernel.org>
Signed-off-by: Andrew Morton <akpm@linux-foundation.org>
Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
On NUMA systems, a node may start thrashing cache or even swap anonymous
pages while there are still free pages on remote nodes.
This is a result of commits 81c0a2bb51 ("mm: page_alloc: fair zone
allocator policy") and fff4068cba ("mm: page_alloc: revert NUMA aspect
of fair allocation policy").
Before those changes, the allocator would first try all allowed zones,
including those on remote nodes, before waking any kswapds. But now,
the allocator fastpath doubles as the fairness pass, which in turn can
only consider the local node to prevent remote spilling based on
exhausted fairness batches alone. Remote nodes are only considered in
the slowpath, after the kswapds are woken up. But if remote nodes still
have free memory, kswapd should not be woken to rebalance the local node
or it may thrash cash or swap prematurely.
Fix this by adding one more unfair pass over the zonelist that is
allowed to spill to remote nodes after the local fairness pass fails but
before entering the slowpath and waking the kswapds.
This also gets rid of the GFP_THISNODE exemption from the fairness
protocol because the unfair pass is no longer tied to kswapd, which
GFP_THISNODE is not allowed to wake up.
However, because remote spills can be more frequent now - we prefer them
over local kswapd reclaim - the allocation batches on remote nodes could
underflow more heavily. When resetting the batches, use
atomic_long_read() directly instead of zone_page_state() to calculate the
delta as the latter filters negative counter values.
Signed-off-by: Johannes Weiner <hannes@cmpxchg.org>
Acked-by: Rik van Riel <riel@redhat.com>
Acked-by: Mel Gorman <mgorman@suse.de>
Cc: <stable@kernel.org> [3.12+]
Signed-off-by: Andrew Morton <akpm@linux-foundation.org>
Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
mem_cgroup_newpage_charge is used only for charging anonymous memory so
it is better to rename it to mem_cgroup_charge_anon.
mem_cgroup_cache_charge is used for file backed memory so rename it to
mem_cgroup_charge_file.
Signed-off-by: Michal Hocko <mhocko@suse.cz>
Cc: Johannes Weiner <hannes@cmpxchg.org>
Signed-off-by: Andrew Morton <akpm@linux-foundation.org>
Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
Some callsites pass a memcg directly, some callsites pass an mm that
then has to be translated to a memcg. This makes for a terrible
function interface.
Just push the mm-to-memcg translation into the respective callsites and
always pass a memcg to mem_cgroup_try_charge().
[mhocko@suse.cz: add charge mm helper]
Signed-off-by: Johannes Weiner <hannes@cmpxchg.org>
Acked-by: Michal Hocko <mhocko@suse.cz>
Signed-off-by: Andrew Morton <akpm@linux-foundation.org>
Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
__mem_cgroup_try_charge duplicates get_mem_cgroup_from_mm for charges
which came without a memcg. The only reason seems to be a tiny
optimization when css_tryget is not called if the charge can be consumed
from the stock. Nevertheless css_tryget is very cheap since it has been
reworked to use per-cpu counting so this optimization doesn't give us
anything these days.
So let's drop the code duplication so that the code is more readable.
Signed-off-by: Michal Hocko <mhocko@suse.cz>
Signed-off-by: Johannes Weiner <hannes@cmpxchg.org>
Signed-off-by: Andrew Morton <akpm@linux-foundation.org>
Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
Instead of returning NULL from try_get_mem_cgroup_from_mm() when the mm
owner is exiting, just return root_mem_cgroup. This makes sense for all
callsites and gets rid of some of them having to fallback manually.
[fengguang.wu@intel.com: fix warnings]
Signed-off-by: Johannes Weiner <hannes@cmpxchg.org>
Signed-off-by: Fengguang Wu <fengguang.wu@intel.com>
Acked-by: Michal Hocko <mhocko@suse.cz>
Signed-off-by: Andrew Morton <akpm@linux-foundation.org>
Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
Users pass either a mm that has been established under task lock, or use
a verified current->mm, which means the task can't be exiting.
Signed-off-by: Johannes Weiner <hannes@cmpxchg.org>
Acked-by: Michal Hocko <mhocko@suse.cz>
Signed-off-by: Andrew Morton <akpm@linux-foundation.org>
Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
Only page cache charges can happen without an mm context, so push this
special case out of the inner core and into the cache charge function.
An ancient comment explains that the mm can also be NULL in case the
task is currently being migrated, but that is not actually true with the
current case, so just remove it.
Signed-off-by: Johannes Weiner <hannes@cmpxchg.org>
Cc: Michal Hocko <mhocko@suse.cz>
Signed-off-by: Andrew Morton <akpm@linux-foundation.org>
Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
mem_cgroup_charge_common() is used by both cache and anon pages, but
most of its body only applies to anon pages and the remainder is not
worth having in a separate function.
Signed-off-by: Johannes Weiner <hannes@cmpxchg.org>
Acked-by: Michal Hocko <mhocko@suse.cz>
Signed-off-by: Andrew Morton <akpm@linux-foundation.org>
Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
It used to disable preemption and run sanity checks but now it's only
taking a number out of one percpu counter and putting it into another.
Do this directly in the callsite and save the indirection.
Signed-off-by: Johannes Weiner <hannes@cmpxchg.org>
Acked-by: Michal Hocko <mhocko@suse.cz>
Signed-off-by: Andrew Morton <akpm@linux-foundation.org>
Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
I tried to use 'dump_page(page, __func__)' for debugging, but it triggers
warning:
warning: passing argument 2 of `dump_page' discards `const' qualifier from pointer target type [enabled by default]
Let's convert 'reason' to 'const char *' in dump_page() and friends: we
shouldn't modify it anyway.
Signed-off-by: Kirill A. Shutemov <kirill.shutemov@linux.intel.com>
Cc: Dave Hansen <dave.hansen@linux.intel.com>
Signed-off-by: Andrew Morton <akpm@linux-foundation.org>
Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
vm_map_ram() has a fragmentation problem when it cannot purge a
chunk(ie, 4M address space) if there is a pinning object in that
addresss space. So it could consume all VMALLOC address space easily.
We can fix the fragmentation problem by using vmap instead of
vm_map_ram() but vmap() is known to be slow compared to vm_map_ram().
Minchan said vm_map_ram is 5 times faster than vmap in his tests. So I
thought we should fix fragment problem of vm_map_ram because our
proprietary GPU driver has used it heavily.
On second thought, it's not an easy because we should reuse freed space
for solving the problem and it could make more IPI and bitmap operation
for searching hole. It could mitigate API's goal which is very fast
mapping. And even fragmentation problem wouldn't show in 64 bit
machine.
Another option is that the user should separate long-life and short-life
object and use vmap for long-life but vm_map_ram for short-life. If we
inform the user about the characteristic of vm_map_ram the user can
choose one according to the page lifetime.
Let's add some notice messages to user.
[akpm@linux-foundation.org: tweak comment text]
Signed-off-by: Gioh Kim <gioh.kim@lge.com>
Reviewed-by: Zhang Yanfei <zhangyanfei@cn.fujitsu.com>
Cc: Minchan Kim <minchan@kernel.org>
Cc: Johannes Weiner <hannes@cmpxchg.org>
Cc: Joonsoo Kim <iamjoonsoo.kim@lge.com>
Signed-off-by: Andrew Morton <akpm@linux-foundation.org>
Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
Add unlikely and likely hints to the function mempool_free. It lays out
the code in such a way that the common path is executed straighforward and
saves a cache line.
Signed-off-by: Mikulas Patocka <mpatocka@redhat.com>
Cc: Ingo Molnar <mingo@elte.hu>
Signed-off-by: Andrew Morton <akpm@linux-foundation.org>
Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
The conditions that control the isolation mode in
isolate_migratepages_range() do not change during the iteration, so
extract them out and only define the value once.
This actually does have an effect, gcc doesn't optimize it itself because
of cc->sync.
Signed-off-by: David Rientjes <rientjes@google.com>
Cc: Mel Gorman <mgorman@suse.de>
Acked-by: Rik van Riel <riel@redhat.com>
Acked-by: Vlastimil Babka <vbabka@suse.cz>
Cc: Joonsoo Kim <iamjoonsoo.kim@lge.com>
Signed-off-by: Andrew Morton <akpm@linux-foundation.org>
Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
The res_counter_{charge,uncharge}_locked() variants are not used in the
kernel outside of the resource counter code itself, so remove the
interface.
Signed-off-by: David Rientjes <rientjes@google.com>
Acked-by: Michal Hocko <mhocko@suse.cz>
Cc: Johannes Weiner <hannes@cmpxchg.org>
Cc: KAMEZAWA Hiroyuki <kamezawa.hiroyu@jp.fujitsu.com>
Cc: Christoph Lameter <cl@linux-foundation.org>
Cc: Pekka Enberg <penberg@kernel.org>
Cc: Tejun Heo <tj@kernel.org>
Cc: Mel Gorman <mgorman@suse.de>
Cc: Oleg Nesterov <oleg@redhat.com>
Cc: Rik van Riel <riel@redhat.com>
Cc: Jianguo Wu <wujianguo@huawei.com>
Cc: Tim Hockin <thockin@google.com>
Cc: Christoph Lameter <cl@linux.com>
Signed-off-by: Andrew Morton <akpm@linux-foundation.org>
Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
PF_MEMPOLICY is an unnecessary optimization for CONFIG_SLAB users.
There's no significant performance degradation to checking
current->mempolicy rather than current->flags & PF_MEMPOLICY in the
allocation path, especially since this is considered unlikely().
Running TCP_RR with netperf-2.4.5 through localhost on 16 cpu machine with
64GB of memory and without a mempolicy:
threads before after
16 1249409 1244487
32 1281786 1246783
48 1239175 1239138
64 1244642 1241841
80 1244346 1248918
96 1266436 1254316
112 1307398 1312135
128 1327607 1326502
Per-process flags are a scarce resource so we should free them up whenever
possible and make them available. We'll be using it shortly for memcg oom
reserves.
Signed-off-by: David Rientjes <rientjes@google.com>
Cc: Johannes Weiner <hannes@cmpxchg.org>
Cc: Michal Hocko <mhocko@suse.cz>
Cc: KAMEZAWA Hiroyuki <kamezawa.hiroyu@jp.fujitsu.com>
Cc: Christoph Lameter <cl@linux-foundation.org>
Cc: Pekka Enberg <penberg@kernel.org>
Cc: Tejun Heo <tj@kernel.org>
Cc: Mel Gorman <mgorman@suse.de>
Cc: Oleg Nesterov <oleg@redhat.com>
Cc: Rik van Riel <riel@redhat.com>
Cc: Jianguo Wu <wujianguo@huawei.com>
Cc: Tim Hockin <thockin@google.com>
Cc: Christoph Lameter <cl@linux.com>
Signed-off-by: Andrew Morton <akpm@linux-foundation.org>
Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
slab_node() is actually a mempolicy function, so rename it to
mempolicy_slab_node() to make it clearer that it used for processes with
mempolicies.
At the same time, cleanup its code by saving numa_mem_id() in a local
variable (since we require a node with memory, not just any node) and
remove an obsolete comment that assumes the mempolicy is actually passed
into the function.
Signed-off-by: David Rientjes <rientjes@google.com>
Acked-by: Christoph Lameter <cl@linux.com>
Cc: Johannes Weiner <hannes@cmpxchg.org>
Cc: Michal Hocko <mhocko@suse.cz>
Cc: KAMEZAWA Hiroyuki <kamezawa.hiroyu@jp.fujitsu.com>
Cc: Christoph Lameter <cl@linux-foundation.org>
Cc: Pekka Enberg <penberg@kernel.org>
Cc: Tejun Heo <tj@kernel.org>
Cc: Mel Gorman <mgorman@suse.de>
Cc: Oleg Nesterov <oleg@redhat.com>
Cc: Rik van Riel <riel@redhat.com>
Cc: Jianguo Wu <wujianguo@huawei.com>
Cc: Tim Hockin <thockin@google.com>
Signed-off-by: Andrew Morton <akpm@linux-foundation.org>
Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
copy_flags() does not use the clone_flags formal and can be collapsed
into copy_process() for cleaner code.
Signed-off-by: David Rientjes <rientjes@google.com>
Cc: Johannes Weiner <hannes@cmpxchg.org>
Cc: Michal Hocko <mhocko@suse.cz>
Cc: KAMEZAWA Hiroyuki <kamezawa.hiroyu@jp.fujitsu.com>
Cc: Christoph Lameter <cl@linux-foundation.org>
Cc: Pekka Enberg <penberg@kernel.org>
Cc: Tejun Heo <tj@kernel.org>
Cc: Mel Gorman <mgorman@suse.de>
Cc: Oleg Nesterov <oleg@redhat.com>
Cc: Rik van Riel <riel@redhat.com>
Cc: Jianguo Wu <wujianguo@huawei.com>
Cc: Tim Hockin <thockin@google.com>
Cc: Christoph Lameter <cl@linux.com>
Signed-off-by: Andrew Morton <akpm@linux-foundation.org>
Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
To increase compiler portability there is <linux/compiler.h> which
provides convenience macros for various gcc constructs. Eg: __weak for
__attribute__((weak)). I've replaced all instances of gcc attributes with
the right macro in the memory management (/mm) subsystem.
[akpm@linux-foundation.org: while-we're-there consistency tweaks]
Signed-off-by: Gideon Israel Dsouza <gidisrael@gmail.com>
Signed-off-by: Andrew Morton <akpm@linux-foundation.org>
Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
This patch is a continuation of efforts trying to optimize find_vma(),
avoiding potentially expensive rbtree walks to locate a vma upon faults.
The original approach (https://lkml.org/lkml/2013/11/1/410), where the
largest vma was also cached, ended up being too specific and random,
thus further comparison with other approaches were needed. There are
two things to consider when dealing with this, the cache hit rate and
the latency of find_vma(). Improving the hit-rate does not necessarily
translate in finding the vma any faster, as the overhead of any fancy
caching schemes can be too high to consider.
We currently cache the last used vma for the whole address space, which
provides a nice optimization, reducing the total cycles in find_vma() by
up to 250%, for workloads with good locality. On the other hand, this
simple scheme is pretty much useless for workloads with poor locality.
Analyzing ebizzy runs shows that, no matter how many threads are
running, the mmap_cache hit rate is less than 2%, and in many situations
below 1%.
The proposed approach is to replace this scheme with a small per-thread
cache, maximizing hit rates at a very low maintenance cost.
Invalidations are performed by simply bumping up a 32-bit sequence
number. The only expensive operation is in the rare case of a seq
number overflow, where all caches that share the same address space are
flushed. Upon a miss, the proposed replacement policy is based on the
page number that contains the virtual address in question. Concretely,
the following results are seen on an 80 core, 8 socket x86-64 box:
1) System bootup: Most programs are single threaded, so the per-thread
scheme does improve ~50% hit rate by just adding a few more slots to
the cache.
+----------------+----------+------------------+
| caching scheme | hit-rate | cycles (billion) |
+----------------+----------+------------------+
| baseline | 50.61% | 19.90 |
| patched | 73.45% | 13.58 |
+----------------+----------+------------------+
2) Kernel build: This one is already pretty good with the current
approach as we're dealing with good locality.
+----------------+----------+------------------+
| caching scheme | hit-rate | cycles (billion) |
+----------------+----------+------------------+
| baseline | 75.28% | 11.03 |
| patched | 88.09% | 9.31 |
+----------------+----------+------------------+
3) Oracle 11g Data Mining (4k pages): Similar to the kernel build workload.
+----------------+----------+------------------+
| caching scheme | hit-rate | cycles (billion) |
+----------------+----------+------------------+
| baseline | 70.66% | 17.14 |
| patched | 91.15% | 12.57 |
+----------------+----------+------------------+
4) Ebizzy: There's a fair amount of variation from run to run, but this
approach always shows nearly perfect hit rates, while baseline is just
about non-existent. The amounts of cycles can fluctuate between
anywhere from ~60 to ~116 for the baseline scheme, but this approach
reduces it considerably. For instance, with 80 threads:
+----------------+----------+------------------+
| caching scheme | hit-rate | cycles (billion) |
+----------------+----------+------------------+
| baseline | 1.06% | 91.54 |
| patched | 99.97% | 14.18 |
+----------------+----------+------------------+
[akpm@linux-foundation.org: fix nommu build, per Davidlohr]
[akpm@linux-foundation.org: document vmacache_valid() logic]
[akpm@linux-foundation.org: attempt to untangle header files]
[akpm@linux-foundation.org: add vmacache_find() BUG_ON]
[hughd@google.com: add vmacache_valid_mm() (from Oleg)]
[akpm@linux-foundation.org: coding-style fixes]
[akpm@linux-foundation.org: adjust and enhance comments]
Signed-off-by: Davidlohr Bueso <davidlohr@hp.com>
Reviewed-by: Rik van Riel <riel@redhat.com>
Acked-by: Linus Torvalds <torvalds@linux-foundation.org>
Reviewed-by: Michel Lespinasse <walken@google.com>
Cc: Oleg Nesterov <oleg@redhat.com>
Tested-by: Hugh Dickins <hughd@google.com>
Signed-off-by: Andrew Morton <akpm@linux-foundation.org>
Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
In shmem/tmpfs, we also use the generic filemap_map_pages, seems the
additional checking is not worth a separate version of map_pages for it.
Signed-off-by: Ning Qu <quning@google.com>
Acked-by: Hugh Dickins <hughd@google.com>
Cc: "Kirill A. Shutemov" <kirill@shutemov.name>
Cc: Mel Gorman <mgorman@suse.de>
Cc: Rik van Riel <riel@redhat.com>
Cc: Dave Hansen <dave.hansen@linux.intel.com>
Cc: Dave Chinner <david@fromorbit.com>
Signed-off-by: Andrew Morton <akpm@linux-foundation.org>
Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
Minor cleanups:
- 'size' variable is now in bytes, not pages;
- use round_up(): it should be easier to read.
Signed-off-by: Kirill A. Shutemov <kirill.shutemov@linux.intel.com>
Cc: Linus Torvalds <torvalds@linux-foundation.org>
Cc: Mel Gorman <mgorman@suse.de>
Cc: Rik van Riel <riel@redhat.com>
Cc: Andi Kleen <ak@linux.intel.com>
Cc: Matthew Wilcox <matthew.r.wilcox@intel.com>
Cc: Dave Hansen <dave.hansen@linux.intel.com>
Cc: Alexander Viro <viro@zeniv.linux.org.uk>
Cc: Dave Chinner <david@fromorbit.com>
Cc: Ning Qu <quning@gmail.com>
Signed-off-by: Andrew Morton <akpm@linux-foundation.org>
Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
Sergey Senozhatsky